Jesper S?rensen wrote:
Problem is, with values high than the tickrate you get a shit load of
local prediction errors, and you really dont want those.
sv_maxupdaterate // Maximum updates per second that the server will allow
--
Chris
___
To
hi,
AMD XP 2800+ Debian Sarge glibc 2.3
15-20% with 12/12
But there are runnig also 2 aother servers on the machine.
1x 16 slots CS 1.6 and 12 Slots Czero
~30 players at this moment
- Original Message -
From: Michael Madsen [EMAIL PROTECTED]
To: [EMAIL PROTECTED]
Sent: Thursday, August
olivier wrote:
This is a multi-part message in MIME format.
--
[ Picked text/plain from multipart/alternative ]
I have 2 identical server
Athlon XP 2000+ 512Mo DDR PC2100
running Linux Debian - Kernel 2.4.23
On the first server hlds takes about 40-60% CPU with 14 players and less
than 10% with 10
some kernels got a /proc/config interface (or similar) but do not ask me
where to find it. some kernel package builders (like the debian one)
place a copy of your config in /boot.
other than that, i don't know where too look for information like that.
best regards,
raoul bhatia
Christopher Luk
DLinkOZ wrote:
Top matches up with what I get via sysstat/mrtg, which polls /proc for it's
info (if I remember correctly). This is on 2.4 kernels.
No wonder, top does poll /proc, too.
Florian
___
To unsubscribe, edit your list preferences, or view the
may be this is a stupid question. how do i know my hz setting? i have
been altering several box on hz but forgot how to extract this value
from the kernerl binary.
chris.
Daniel Stroven wrote:
2.4.x kernels do not show truly accurate results, this has been argued on
this list many times.
Then can we ask what optimizations you are using alfred?
Right now with a full server I am getting 80 fps
ticrate 1000
hz = 1000
How did alfreds server play with an avg 50 ping? I never got a chance to
play test it.
Kenny
- Original Message -
From: Alfred Reynolds [EMAIL PROTECTED]
To:
Sindre wrote:
Numbers lie, the p2 cache (even p3 katmai, not coppermine) is 512kb, but it's
sloow, so the new cache is extremly, by far, more superior.
It's better yes, but that is not always relevant. You have to also
factor in where your bottleneck is. If the problem is that the data
Try running a Tactical Ops server with TOP3 and check a nice 95% CPU
usage for a single server, no matter if there's 4 or 30 players on the
server... Compared to TO + TOP3, HL is not that bad, is it ?
nelson
Stefan Huszics wrote:
Sindre wrote:
Numbers lie, the p2 cache (even p3 katmai, not
: Re: [hlds_linux] CPU usage
Marcelo Bezerra wrote:
If he is profiling to decrease cpu load, a slow machine will more
clearly show problems.
Yes, but on the other hand a P2 is different enough from a P4 that a
possible error in the code might not show.
Also, even though the P2 is slow
I only mention the maps majority of servers play. Pirensi is bad as
well..but just named the 2 :)
- Original Message -
From: Stefan Huszics [EMAIL PROTECTED]
To: [EMAIL PROTECTED]
Sent: Friday, January 23, 2004 12:24 AM
Subject: Re: [hlds_linux] CPU usage
Daniel Stroven wrote:
aztec
- ill even GIVE you my old 1.6Ghz if you promise to fix the problem!
James
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Alfred
Reynolds
Sent: 23 January 2004 05:14
To: [EMAIL PROTECTED]
Subject: RE: [hlds_linux] CPU usage
playtest:/usr/src/oprofile-0.7.1
PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of
Justin Mitchell
Sent: Thursday, January 22, 2004 10:56 PM
To: [EMAIL PROTECTED]
Subject: Re: [hlds_linux] CPU usage
Hey, we got 12 on there before the cpu maxed out!
James Sykes wrote:
Good luck with a p333, however I think you will have
was
for research, I just don't want you thinking it never lagged because it was
constantly lagging.
- Original Message -
From: Alfred Reynolds [EMAIL PROTECTED]
To: [EMAIL PROTECTED]
Sent: Thursday, January 22, 2004 11:20 PM
Subject: RE: [hlds_linux] CPU usage
I will be doing some testing
Mitchell
Sent: Thursday, January 22, 2004 10:56 PM
To: [EMAIL PROTECTED]
Subject: Re: [hlds_linux] CPU usage
Hey, we got 12 on there before the cpu maxed out!
James Sykes wrote:
Good luck with a p333, however I think you will have a hard
time getting
more than 4 players on at a time :) Time
[EMAIL PROTECTED] wrote:
I will be doing some testing on P4's, but we had to start somewhere.
The PII 333 handled 13 players just fine on aztec.
I need more continuous player numbers before I can swap in the newer
binary, hopefully the word will spread overnight (my night).
Advertise that
PROTECTED] On Behalf Of
Jason Y. tail
Sent: Thursday, January 22, 2004 11:41 PM
To: [EMAIL PROTECTED]
Subject: Re: [hlds_linux] CPU usage
Were you in the server? Just to let you know, it DID lag
with 13 players on
de_aztec when I was in there. I ping 20-30ms to the server
PM
To: [EMAIL PROTECTED]
Subject: Re: [hlds_linux] CPU usage
Were you in the server? Just to let you know, it DID lag
with 13 players on
de_aztec when I was in there. I ping 20-30ms to the server,
but in the
game, I was getting no lower than 90, as with everyone else,
which leads me
to believe
where is the server located?
- Original Message -
From: Alfred Reynolds [EMAIL PROTECTED]
To: [EMAIL PROTECTED]
Sent: Friday, January 23, 2004 7:09 PM
Subject: RE: [hlds_linux] CPU usage
If you do play on the server and experiencing gameplay like this can you
send me the time it happen
PROTECTED]
Subject: Re: [hlds_linux] CPU usage
Ya could just write a simple script that monitors how many players are
in there, and gets the mix/max/avg ping. Plot that against the rest of
your numbers and ya should have some good stuff to look at.
Alfred Reynolds wrote:
If you do play
Unfortunately I keep getting swedes with 200+ pings joining the server
throwing the numbers out ;-) I keep the idea in mind however.
sort by ip, netblock, country?
;)
Silly Swedes!
Thanks
-a-
P.S. Working a late night?
Adam 'Starblazer'
Washington, USA.
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of mvettas
Sent: Friday, January 23, 2004 12:18 AM
To: [EMAIL PROTECTED]
Subject: Re: [hlds_linux] CPU usage
where is the server located?
- Original Message -
From: Alfred
Matthew Donnon wrote:
uh Stefan,
current p4 cpus (533 and 800 fsb) have exactly the same amount of L2 cache
as the p2 (512k).
Older (400fsb) units had 1/2 the amount (256k)
512k / 3000MHz = ?
512k / 333MHz = ?
I'm sure running a 10 player server on a 333MHZ comp is ok, but it's not
ok for a
: Friday, 23 January 2004 5:02 p.m.
To: [EMAIL PROTECTED]
Subject: RE: [hlds_linux] CPU usage
It is a default config (the only tweak being the name and sv_region). It
is also NOT running any plugins. I am using the current setup to get a
good baseline of performance for this particular hardware
a
good baseline of performance for this particular hardware combo.
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of
Mike Kercher
Sent: Thursday, January 22, 2004 7:06 PM
To: [EMAIL PROTECTED]
Subject: RE: [hlds_linux] CPU usage
I'd be curious to know
Alfred Reynolds wrote:
The machine is a dual 1.4GHz PII
Is that really true? 1.4GHz P2...in dual config?
--
Eric (the Deacon remix)
___
To unsubscribe, edit your list preferences, or view the list archives, please visit:
]
[mailto:[EMAIL PROTECTED] On Behalf Of
Eric (Deacon)
Sent: Thursday, January 22, 2004 8:48 PM
To: [EMAIL PROTECTED]
Subject: Re: [hlds_linux] CPU usage
Alfred Reynolds wrote:
The machine is a dual 1.4GHz PII
Is that really true? 1.4GHz P2...in dual config?
--
Eric (the Deacon remix
Daniel Stroven wrote:
aztec and office are the highest cpu usage maps of the default maps, with
cbble being not far behind those.
Ehh, what about de_torn, de_chateau and the real killer cs_havanna ...
--
/Stefan
Software never has bugs. It just develops random features. =)
-
From: Alfred Reynolds [EMAIL PROTECTED]
To: [EMAIL PROTECTED]
Sent: Thursday, January 22, 2004 11:13 PM
Subject: RE: [hlds_linux] CPU usage
playtest:/usr/src/oprofile-0.7.1# cat /proc/cpuinfo
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 5
model
!
James
-Original Message-
From: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] On Behalf Of Alfred
Reynolds
Sent: 23 January 2004 05:14
To: [EMAIL PROTECTED]
Subject: RE: [hlds_linux] CPU usage
playtest:/usr/src/oprofile-0.7.1# cat /proc/cpuinfo
processor : 0
vendor_id : GenuineIntel
On Fri, 4 Jul 2003, James Clark wrote:
On Fri, Jul 04, 2003 at 01:37:12AM -0400, Daniel Stroven wrote:
This is a multi-part message in MIME format.
--
[ Picked text/plain from multipart/alternative ]
de_aztec with 22/24
1:27am up 1 day, 5:33, 2 users, load average: 2.32, 2.17,
i've noticed a slow increase in Server CPU usae with each of the Vac
updates. Its Almost as bad as HLG used to be, But you can't configure VAC
like you can HLG
- Original Message -
From: Justin Mitchell [EMAIL PROTECTED]
To: [EMAIL PROTECTED]
Sent: Friday, February 14, 2003 6:10 PM
At Friday 01:10 PM 2/14/2003 -0500, you wrote:
Has anyone else noticed a huge cpu increase since last night? Each of my
servers (hosted on different boxes) are using nearly twice what they used
before. Was their a VAC update that I was unaware of?
VAC update? LOL.. right.
Jay
Jay Carter
I would never have considered running AMDs in a 1u rack
mount regardless.
but if you did, I could see that heat could become a small problem,
especially if you cramming a few high speed HDDs into that
small space as
well. Satndard mini tower with front and back fans seems
to run at
Anyone out there using TEC modules (Thermo-electric cooling
AKA Peltier
device) ? I am really looking into it for a dual P3 system.
About the only people using peltiers are serious overclockers. If you put
them inside a server (especially a small one like 1U or 2U), they'll have to
be
There are lot of 1U servers that run dual AMD's. Can't understand why some of
you don't think it's any good. Sure there is some cost to develop the 1U
chassis and the one who has to pay is the customer. But if you need the space
to other things, well then there's really not much to do than to
You'll need (stan?) about 3x the airflow to keep this monster
at a decent temperature.
I won't even guess at a ratio. I just wouldn't run peltiers in a server at
all, especially a 1U or 2U.
Most Peltier using overclockers tend to couple them with
water cooling as its
heat carrying
Quoting Adam Hobbs [EMAIL PROTECTED]:
As long as heat/power is not an issue.
8-))
When has heat ever been an issue in an airconditioned rack in an
climate controlled data centre?
Having 19°C in the rack and in the datacentre is nice.
Having more than 70°C in the 1U case (or even 2U),
PROTECTED]
Subject: RE: [hlds_linux] CPU Usage?
what operating system? you try the latest det 40s that were
released teh other day?
kev
-Original Message-
From: [EMAIL PROTECTED]
[mailto:hlds_linux-admin;list.valvesoftware.com]On Behalf Of Eric
(Deacon)
Sent: Sunday, November 10, 2002 1:36 AM
As long as heat/power is not an issue.
8-))
David.
--
When has heat ever been an issue in an airconditioned rack in an climate
controlled data centre?
:)
mentasm
___
To unsubscribe, edit your list preferences, or view the list archives,
On Mon, 2002-11-11 at 15:40, Adam Hobbs wrote:
When has heat ever been an issue in an airconditioned rack in an climate
controlled data centre?
regardless of how well cooled you rack is, internal case temps need kept
down.
We have just had to upgrade to a 2u case from a 1u with a dual amd
On Mon, 2002-11-11 at 15:40, Adam Hobbs wrote:
When has heat ever been an issue in an airconditioned rack in an climate
controlled data centre?
regardless of how well cooled you rack is, internal case temps need kept
down.
We have just had to upgrade to a 2u case from a 1u with a dual
host_speeds 0/1
-Original Message-
From: [EMAIL PROTECTED]
[mailto:hlds_linux-admin;list.valvesoftware.com]On Behalf Of Eric
(Deacon)
Sent: Sunday, November 10, 2002 6:22 PM
To: [EMAIL PROTECTED]
Subject: RE: [hlds_linux] CPU Usage?
N00b question #1 (for the day)
How do I get my
conditioning blew.
kev
-Original Message-
From: [EMAIL PROTECTED]
[mailto:hlds_linux-admin;list.valvesoftware.com]On Behalf Of Adam Hobbs
Sent: Sunday, November 10, 2002 9:41 PM
To: [EMAIL PROTECTED]
Subject: RE: P3 vs P4 vs Athlon was: Re: [hlds_linux] CPU Usage?
As long as heat/power
PROTECTED]
Subject: Re: [hlds_linux] CPU Usage?
Have you turned off the HLGuard wallhack block feature? Combining that with
the VAC's wallhack block can cause high CPU usage.
-Disk2
- Original Message -
From: matthew gossage [EMAIL PROTECTED]
To: [EMAIL PROTECTED]
Sent: Saturday, November
, not sure
which it was.
- Original Message -
From: matthew gossage [EMAIL PROTECTED]
To: [EMAIL PROTECTED]
Sent: Saturday, November 09, 2002 4:36 PM
Subject: Re: [hlds_linux] CPU Usage?
just trying the no hlguard wallhack.
I'm not mad
a P4 2.0 should be able to run atleast 3 18 mans
PROTECTED]
Sent: Saturday, November 09, 2002 6:56 PM
Subject: RE: [hlds_linux] CPU Usage?
Does VAC have the wallhack yet? I know it was supposed to but I don't
rememeber hearing if it's been done yet or not.
-Original Message-
From: [EMAIL PROTECTED]
[mailto:hlds_linux-admin
a P4 2.0 should be able to run atleast 3 18 mans servers
Should'nt it
My AthlonXP 1900+ and overclocked Ti4200 should be able to keep CS at
100fps no matter what, but it doesn't either :\
--
Eric (the Deacon remix)
___
To unsubscribe, edit your
]
Subject: RE: [hlds_linux] CPU Usage?
a P4 2.0 should be able to run atleast 3 18 mans servers
Should'nt it
My AthlonXP 1900+ and overclocked Ti4200 should be able to keep CS at
100fps no matter what, but it doesn't either :\
--
Eric (the Deacon remix
Quoting Oscar [EMAIL PROTECTED]:
Someone said that he couldn't think of any other reason than VAC for
the problem, but as I mentioned erlier there are no difference if the
server is in secure mode or not. The CPU usage is the same...
Same results here for the same test : it is not VSM.
The
Quoting Oscar [EMAIL PROTECTED]:
Hmm, I discovered something... The pingboost option 1 and 2 seems to
double the CPU usage!?!
They have increased the CPU usage but never doubled it...
Is this the way it's suposed to be or is it some bug? I'm thinking
that it is running in pingboost mode 3
Quoting Oscar [EMAIL PROTECTED]:
No I have not tried the beta...
Does it fix the problem or have you even tried it? :)
No I did not.
I won't have time before beginning of next week fortesting them either.
But next week I'll re-install from scratch the four 16 slots servers, with the beta
The same problem exist when you launch the HL/CS servers in insecure mode.
At least at our debian server, don't know about freebsd...
The only way I find to defeat the high CPU usage is to turn of the
pingbooster...
/Oscar, www.bhood.nu
Quoting David Touitou [EMAIL PROTECTED]:
Quoting Oscar
Or there's a huge bug somewhere (the tried I made show me than only
pingboost 3 was a CPU eater (doubler or nearly), whereas the only
pingboost option that gave us a lower ping with FreeBSD).
David.
Are you absolutely sure about this? I seam to remember that ping boost
has no effect on
Quoting m0gely [EMAIL PROTECTED]:
Or there's a huge bug somewhere (the tried I made show me than
only pingboost 3 was a CPU eater (doubler or nearly), whereas the
only pingboost option that gave us a lower ping with FreeBSD).
David.
Are you absolutely sure about this? I seam to
to
be at play.
- Original Message -
From: m0gely [EMAIL PROTECTED]
To: [EMAIL PROTECTED]
Sent: Thursday, September 12, 2002 7:56 AM
Subject: RE: [hlds_linux] CPU usage problem
Or there's a huge bug somewhere (the tried I made show me than only
pingboost 3 was a CPU eater (doubler
Ive noticed the same thing. My servers are hogging the system.
The only thing i can think of is VAC.
My system is running on FreeBSD with dual PIII 500.
A couple days ago I was able to run them flawlessly on that HW. but today
its impossible. Even on the matchserver where we only run VAC,
101 - 157 of 157 matches
Mail list logo